基于神经元控制的网络时延补偿策略研究

针对网络控制系统（NCS）中的不确定时延问题,在分析循环服务网络和随机争用网络的时延特性的基础上,提出了一种基于神经元控制器的时延补偿策略.该策略用神经元控制代替常规PID控制,无需建立网络控制系统的精确模型,利用神经元良好的学习能力来克服网络控制系统中不确定时延的影响,并对循环服务网络和随机争用网络这两类网络进行了仿真实验研究.仿真结果表明该策略能保证网络控制系统的良好性能.     

随机二元神经网络的学习与泛化

本文提出了一种采用随机加权联接的新型神经网络模型,该模型具有清晰可分析的神经元激活函数,内部数据表示为随机二进制序列形式,硬件实现十分简洁高效.本文在三个不同层次对前向型网络的学习算法和系统仿真进行了深入的讨论,其中最底层的学习对应于硬件实时在线学习.另外,本文还对系统的泛化性能作了全面的分析,给出了VC维和学习样本量的明确结果.通过对三个用于标准测试的Monk问题和数字手写体识别问题的检测,获得了很好的实验结果.     

基于样条权函数神经网络的入侵检测*

通过分析当前运用较多的入侵检测模型的缺陷,提出了一种基于样条权函数神经网络的新型入侵检测系统模型。网络拓扑结构简单,网络训练所需要的神经元个数与样本个数无关。训练后的权函数由三次样条函数构成,而不是传统方法中的常数。该模型克服了传统入侵检测系统所存在的局部极小、收敛速度慢、初值敏感性等问题。     

几何学概率的无线传感器网络能耗估计模型

针对无线传感器网络能耗这一问题,提出了一种基于几何学概率的能耗估计模型.以节点的状态转换为基础,建立了基于半Markov链的节点能耗模型,并引入概率分布函数的概念.从传感器节点随机分布出发,假定节点之间可以相互通信,分别对在单个正六边形和相邻两个正六边形内的节点随机分布进行研究,推导得出能耗估计模型.仿真结果表明:该模型可以实现网络能耗的准确估计.     

平稳动态系统DBN结构学习模型设计

针对动态数据挖掘问题,提出了一种平稳系统连续变量动态贝叶斯网络(Dynamic Bayesian Networks,DBN)结构学习模型,用于智能体的自主优化;首先给出了平稳系统连续变量结构学习的基本思路及假设条件,讨论了平稳系统连续变量DBN结构学习的模型设计问题;其次,在诸多随机过程系统文献的基础上.提出了系统的BIC评分函数,在有限时间T内的情况给出三个定义,并设计了学习的基本框架;最后,设计了平稳系统连续变量的实验模型并进行了仿真,结果表明,该模型能正确地学习出所设计的DBN结构.     

贝叶斯缺陷分析模型及其在软件测试中的应用

针对面向对象软件提出了一种以贝叶斯网络理论为基础的软件缺陷分析模型,通过分析系统中存在缺陷对象之间的影响关系构建贝叶斯网络模型,利用已有的经验数据评估贝叶斯网络模型中各节点的缺陷概率分布,并与软件测试过程相结合,直接从测试设计级别为测试人员提供相关决策支持。将该模型应用到实际的项目中,取得了较好的效果。     

一类概率依赖的随机网络系统的随机容错设计

针对网络控制系统的传感器、执行器和网络时延具有随机性这一现象,引入相互独立的Bernoulli随机变量序列作为传感器失效故障、执行器失效故障的开关矩阵,将时延的变化区间任意分成两个小区间,引进Bernoulli随机变量并将其概率分布引入到系统矩阵中,建立随机的网络化控制系统模型,研究了该系统存在传感器失效故障、执行器失效故障及二者同时失效故障情况下的随机容错控制问题。基于Lyapunov稳定性理论,结合线性矩阵不等式技术,给出了确保系统均方指数稳定的条件,该条件不仅依赖于时延的上下界,还依赖于时延的概率分布。数值实例说明结论是有效的。     

增量型极限学习机改进算法

增量型极限学习机（incremental extreme learning machine,I-ELM）在训练过程中,由于输入权值及隐层神经元阈值的随机获取,造成部分隐层神经元的输出权值过小,使其对网络输出贡献小,从而成为无效神经元．这个问题不但使网络变得更加复杂,而且降低了网络的稳定性．针对此问题,本文提出了一种给I-ELM隐层输出加上偏置的改进方法（即Ⅱ-ELM）,并分析证明了该偏置的存在性．最后对I-ELM方法在分类和回归问题上进行仿真对比,验证Ⅱ-ELM的有效性.     

一种新型的动态递归神经网络及其算法

通过对Elman网络的研究 ,提出了一种新型的基于输入层、隐层、输出层神经元递归的动态递归神经网络 ,并给出了其算法。通过在系统辨识中的应用表明 ,该网络收敛速度快 ,模型精度高 ,具有较为广阔的应用前景。     

基于概率分布代表点的模型集合设计方法

对于估计、滤波和控制等问题, 多模型方法提供了一种非常优越的解决方案. 设计优良的模型集合是应用多模型方法的首要问题. 本文提出了一种基于概率分布代表点的模型集合设计方法. 在已知系统模式的概率分布条件下, 由数论方法获得代表其概率分布的F–偏差或伪F–偏差代表点和均方差代表点, 利用这些代表点构成覆盖系统模式空间的模型集合. 文中给出了一维和二维模型集合的具体设计. 仿真结果说明了所设计的模型集合的性能.     

A recurrent stochastic binary network

Stochastic neural networks are usually built by introducing random fluctuations into the network. A natural method is to use stochastic connections rather than stochastic activation functions. We propose a new model in which each neuron has very simple functionality but all the connections are stochastic. It is shown that the stationary distribution of the network uniquely exists and it is approxi-mately a Boltzmann-Gibbs distribution. The relationship between the model and the Markov random field is discussed. New techniques to implement simulated annealing and Boltzmann learning are pro-posed. Simulation results on the graph bisection problem and image recognition show that the network is powerful enough to solve real world problems.     

一种新型随机二进制神经网络

二进制数据表示具有简洁高效的特点,随机噪声有助于系统摆脱局部极小.新型的随 机神经网络模型采用随机加权联接,内部数据表示为随机二进制序列形式,实现十分高效.文中 分别就前馈型网络和反馈型网络进行了深入的讨论,给出了前馈型网络的梯度下降学习算法, 为反馈型网络设计了快速有效的模拟退火算法和渐进式Boltzmann学习算法.通过对PARITY 问题的测试,发现了新模型的一些有趣特征,实验结果表明梯度下降学习效果显著.利用渐进式 Boltzmann学习,反馈型网络被成功地用于带噪声人脸识别.     

复杂运动目标的学习与识别

针对复杂运动目标识别问题,提出了一个基于反馈型随机神经网络的运动认脸与物体的自动识别系统,该系统具有强大学习能力,运动目标检测与识别快速准确等特点,在对该的核心－反馈型二元网络进行深入分析的基础上,提出了一种适合于该神经网络模型的高效渐进式Boltzmann学习算法,实验结果表明,该识别系统性能优异,在几个方面超过了eTrue公司的TrueFace人脸识别系统。     

Information geometry of Boltzmann machines

A Boltzmann machine is a network of stochastic neurons. The set of all the Boltzmann machines with a fixed topology forms a geometric manifold of high dimension, where modifiable synaptic weights of connections play the role of a coordinate system to specify networks. A learning trajectory, for example, is a curve in this manifold. It is important to study the geometry of the neural manifold, rather than the behavior of a single network, in order to know the capabilities and limitations of neural networks of a fixed topology. Using the new theory of information geometry, a natural invariant Riemannian metric and a dual pair of affine connections on the Boltzmann neural network manifold are established. The meaning of geometrical structures is elucidated from the stochastic and the statistical point of view. This leads to a natural modification of the Boltzmann machine learning rule.     

Random network models and sensitivity algorithms for the analysis of ordering time and inventory state in multi-stage supply chains

Supply chains in reality face a highly dynamic and uncertain environment, especially the uncertain end-customer demands and orders. Since the condition of product market changes frequently, the tasks of order management, product planning, and inventory management are complex and difficult. It is imperative for companies to develop new ways to manage the randomness and uncertainty in market demands. Based on the graphical evaluation and review technique, this paper provides a simple but integrated stochastic network mathematical model for supply chain ordering time distribution analysis. Then the ordering time analysis model is extended so that the analysis of inventory level distribution characteristics of supply chain members is allowed. Further, to investigate the effects of different end-customer demands on upstream orders and relative inventory levels, model-based sensitivity analysis algorithms for ordering fluctuations and inventory fluctuations are developed. A detailed numerical example is presented to illustrate the application of the proposed models to a multi-stage supply chain system, and the results of which shows the effectiveness and flexibility of the proposed stochastic network models and algorithms in order and inventory management.     

用遗传算法优化Boltzmann机

Boltzmann机是一种应用广泛的随机神经网络。它通过模拟退火算法进行网络学习,能取得一个全局或接近全局最优的最优值;通过期望网络模式和实际学习得到的网络模式比较来调节网络的权值,使网络能尽可能地达到或逼近期望的网络模式。将遗传算法运用到Boltzmann机的网络学习中,在对BM机编码后,通过选择、交叉和变异等遗传操作算子对网络进行训练,调整网络的权值,使适应度函数值大的网络保留下来,最终使网络达到期望的模式。通过实例验证,这是一种简单可行的调节网络权值的方法。     

Block sampler and posterior mode estimation for asymmetric stochastic volatility models

A new efficient simulation smoother and disturbance smoother are introduced for asymmetric stochastic volatility models where there exists a correlation between today's return and tomorrow's volatility. The state vector is divided into several blocks where each block consists of many state variables. For each block, corresponding disturbances are sampled simultaneously from their conditional posterior distribution. The algorithm is based on the multivariate normal approximation of the conditional posterior density and exploits a conventional simulation smoother for a linear and Gaussian state-space model. The performance of our method is illustrated using two examples: (1) simple asymmetric stochastic volatility model and (2) asymmetric stochastic volatility model with state-dependent variances. The popular single move sampler which samples a state variable at a time is also conducted for comparison in the first example. It is shown that our proposed sampler produces considerable improvement in the mixing property of the Markov chain Monte Carlo chain.     

Markov Chain Monte Carlo for Automated Face Image Analysis

We present a novel fully probabilistic method to interpret a single face image with the 3D Morphable Model. The new method is based on Bayesian inference and makes use of unreliable image-based information. Rather than searching a single optimal solution, we infer the posterior distribution of the model parameters given the target image. The method is a stochastic sampling algorithm with a propose-and-verify architecture based on the Metropolis–Hastings algorithm. The stochastic method can robustly integrate unreliable information and therefore does not rely on feed-forward initialization. The integrative concept is based on two ideas, a separation of proposal moves and their verification with the model (Data-Driven Markov Chain Monte Carlo), and filtering with the Metropolis acceptance rule. It does not need gradients and is less prone to local optima than standard fitters. We also introduce a new collective likelihood which models the average difference between the model and the target image rather than individual pixel differences. The average value shows a natural tendency towards a normal distribution, even when the individual pixel-wise difference is not Gaussian. We employ the new fitting method to calculate posterior models of 3D face reconstructions from single real-world images. A direct application of the algorithm with the 3D Morphable Model leads us to a fully automatic face recognition system with competitive performance on the Multi-PIE database without any database adaptation.     

Learning to design synergetic computers with an extended symmetric diffusion network.

This article proposes an extended symmetric diffusion network that is applied to the design of synergetic computers. The state of a synergetic computer is translated to that of order parameters whose dynamics is described by a stochastic differential equation. The order parameter converges to the Boltzmann distribution, under some condition on the drift term, derived by the Fokker-Planck equation. The network can learn the dynamics of the order parameters from a nonlinear potential. This property is necessary to design the coefficient values of the synergetic computer. We propose a searching function for the image processing executed by the synergetic computer. It is shown that the image processing with the searching function is superior to the usual image-associative function of synergetic computation. The proposed network can be related, as a special case, to the discrete-state Boltzmann machine by some transformation. Finally, the extended symmetric diffusion network is applied to the estimation problem of an entire density function, as well as the proposed searching function for the image processing.     

A new real-coded stochastic Bayesian optimization algorithm for continuous global optimization

Estimation of distribution algorithms are considered to be a new class of evolutionary algorithms which are applied as an alternative to genetic algorithms. Such algorithms sample the new generation from a probabilistic model of promising solutions. The search space of the optimization problem is improved by such probabilistic models. In the Bayesian optimization algorithm (BOA), the set of promising solutions forms a Bayesian network and the new solutions are sampled from the built Bayesian network. This paper proposes a novel real-coded stochastic BOA for continuous global optimization by utilizing a stochastic Bayesian network. In the proposed algorithm, the new Bayesian network takes advantage of using a stochastic structure (that there is a probability distribution function for each edge in the network) and the new generation is sampled from the stochastic structure. In order to generate a new solution, some new structure, and therefore a new Bayesian network is sampled from the current stochastic structure and the new solution will be produced from the sampled Bayesian network. Due to the stochastic structure used in the sampling phase, each sample can be generated based on a different structure. Therefore the different dependency structures can be preserved. Before the new generation is generated, the stochastic network’s probability distributions are updated according to the fitness evaluation of the current generation. The proposed method is able to take advantage of using different dependency structures through the sampling phase just by using one stochastic structure. The experimental results reported in this paper show that the proposed algorithm increases the quality of the solutions on the general optimization benchmark problems.